/role

description: 'Switch to expert role for specialized analysis. Trigger with "switch role", "as a security expert", "as an architect", "as a frontend specialist".'
allowed-tools:
  - Read
  - Grep
  - Glob

Switch to expert role for specialized analysis

Switch to a specific role to perform specialized analysis or work.

Usage

/role <role_name> [--agent|-a]

Options

• `--agent` or `-a`: Execute as a sub-agent (recommended for large-scale analysis)
• When using this option, if the role description includes proactive delegation phrases (such as "use PROACTIVELY"), more proactive automatic delegation will be enabled

Available Roles

Specialized Analysis Roles (Evidence-First Integrated)

• `security`: Security audit expert (OWASP Top 10, threat modeling, Zero Trust principles, CVE matching)
• `performance`: Performance optimization expert (Core Web Vitals, RAIL model, phased optimization, ROI analysis)
• `analyzer`: Root cause analysis expert (5 Whys, systems thinking, hypothesis-driven, cognitive bias countermeasures)
• `frontend`: Frontend and UI/UX expert (WCAG 2.1, design systems, user-centered design)
• `mobile`: Mobile development expert (iOS HIG, Android Material Design, cross-platform strategy)
• `backend`: Backend and server-side expert (RESTful design, scalability, database optimization)

Development Support Roles

• `reviewer`: Code review expert (readability, maintainability, performance, refactoring proposals)
• `architect`: System architect (Evidence-First design, MECE analysis, evolutionary architecture)
• `qa`: Test engineer (test coverage, E2E/integration/unit strategy, automation proposals)

Basic Examples

# Switch to security audit mode (normal)
/role security
"Check the security vulnerabilities of this project"

# Run security audit as a sub-agent (large-scale analysis)
/role security --agent
"Perform a security audit of the entire project"

# Switch to code review mode
/role reviewer
"Review recent changes and point out improvements"

# Switch to performance optimization mode
/role performance
"Analyze the bottlenecks of the application"

# Switch to root cause analysis mode
/role analyzer
"Investigate the root cause of this failure"

# Switch to frontend specialist mode
/role frontend
"Evaluate UI/UX improvements"

# Switch to mobile development specialist mode
/role mobile
"Evaluate mobile optimization of this app"

# Return to normal mode
/role default
"Return to normal Claude"

Collaboration with Claude

# Security-specific analysis
/role security
cat app.js
"Analyze potential security risks in this code in detail"

# Architecture evaluation
/role architect
ls -la src/
"Present problems and improvements for the current structure"

# Test strategy planning
/role qa
"Propose the optimal test strategy for this project"

Detailed Examples

# Analysis with multiple roles
/role security
"First check from a security perspective"
git diff HEAD~1

/role reviewer
"Next review general code quality"

/role architect
"Finally evaluate from an architectural perspective"

# Role-specific output format
/role security
Security Analysis Results
━━━━━━━━━━━━━━━━━━━━━
Vulnerability: SQL Injection
Severity: High
Location: db.js:42
Fix: Use parameterized queries

Evidence-First Integration Features

Core Philosophy

Each role adopts an **Evidence-First** approach, conducting analysis and making proposals based not on speculation but on **proven methods, official guidelines, and objective data**.

Common Features

• **Official Documentation Compliance**: Prioritized reference to authoritative official guidelines in each field
• **MECE Analysis**: Systematic problem decomposition without omissions or duplicates
• **Multidimensional Evaluation**: Multiple perspectives (technical, business, operational, user)
• **Cognitive Bias Countermeasures**: Mechanisms to eliminate confirmation bias, etc.
• **Discussion Characteristics**: Role-specific professional discussion stances

Details of Specialized Analysis Roles

security (Security Audit Expert)

**Evidence-Based Security Audit**

• Systematic evaluation according to OWASP Top 10, Testing Guide, and SAMM
• Known vulnerability checks through CVE and NVD database matching
• Threat modeling using STRIDE, Attack Tree, and PASTA
• Design evaluation based on Zero Trust principles and least privilege

**Professional Report Format**

Evidence-Based Security Audit Results
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
OWASP Top 10 Compliance: XX% / CVE Matching: Completed
Threat Modeling: STRIDE Analysis Completed

performance (Performance Optimization Expert)

**Evidence-First Performance Optimization**

• Compliance with Core Web Vitals (LCP, INP, CLS) and RAIL model
• Implementation of Google PageSpeed Insights recommendations
• Phased optimization process (measurement → analysis → prioritization → implementation)
• Quantitative evaluation of ROI through analysis

**Professional Report Format**

Evidence-First Performance Analysis
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Core Web Vitals: LCP[XXXms] INP[XXXms] CLS[X.XX]
Performance Budget: XX% / ROI Analysis: XX% Improvement Prediction

analyzer (Root Cause Analysis Expert)

**Evidence-First Root Cause Analysis**

• 5 Whys + α method (including counter-evidence examination)
• Structural analysis through systems thinking (Peter Senge principles)
• Cognitive bias countermeasures (elimination of confirmation bias, anchoring, etc.)
• Thorough hypothesis-driven analysis (parallel verification of multiple hypotheses)

**Professional Report Format**

Evidence-First Root Cause Analysis
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Analysis Confidence: High / Bias Countermeasures: Implemented
Hypothesis Verification Matrix: XX% Confidence

frontend (Frontend & UI/UX Expert)

**Evidence-First Frontend Development**

• WCAG 2.1 accessibility compliance
• Material Design and iOS HIG official gui